automatically generating gene summaries from biomedical literature

Automatically Generating Gene Summaries from Biomedical

Literature(Ling et al. PSB 2006)

CS 466Lecture by: Xin He, Ph.D. candidate,

Bioinformatics group, UIUC.(Slides courtesy of Xu Ling, UIUC)

Outline

• Introduction– Motivation

• System– Keyword Retrieval Module– Information Extraction Module

• Experiments and Evaluations

• Conclusion and Future Work

Motivation

• Finding all the information we know about a gene from the literature is a critical task in biology research

• Reading all the relevant articles about a gene is time consuming

• A summary of what we know about a gene would help biologists to access the already-discovered knowledge

An Ideal Gene Summary• http://flybase.org/reports/FBgn0000017.html

GP

EL

SI

GI

MP

WFPI

Above summary is from ca. 2006

Problem with Current Situation?

• Manually generated

• Labor-intensive

• Hard to keep updated with the rapid growth of the literature information

How can we generate such summaries automatically?

The solution

• Structured summary on 6 aspects1. Gene products (GP)

2. Expression location (EL)

3. Sequence information (SI)

4. Wild-type function and phenotypic information (WFPI)

5. Mutant phenotype (MP)

6. Genetic interaction (GI)

• 2-stage summarization– Retrieve relevant articles

by keyword match

– Extract most informative and relevant sentences for 6 aspects.

Outline

• Introduction– Motivation

• System– Keyword Retrieval Module– Information Extraction Module

• Experiments and Evaluations

• Conclusion and Future Work

System Overview: 2-stage

IE = Information Extraction; KR = Keyword Retrieval

Keyword Retrieval Module

• Dictionary-based keyword retrieval: to retrieve all documents containing any synonyms of the target gene.

– Input: gene name– Output: relevant documents for that gene

1. Gene SynSet Construction

2. Keyword-based retrieval

KR module

Gene SynSet Construction &Keyword Retrieval

• Gene SynSet: a set of synonyms of the target gene• Issues in constructing SynSet

– Variation in gene name spelling• gene cAMP dependent protein kinase 2:

PKA C2, Pka C2, Pka-C2,…• normalized to “pka c 2”

– Short names are sometimes ambiguous, e.g., gene name “PKA” is also a chemical term

– Require retrieved document to have at least one synonym that is >= 5 characters long

• Retrieving documents based on keywords: Enforce the exact match of the token sequence

Information Extraction Module

• Takes a set of documents returned from the KR module, and extracts sentences that contain useful factual information about the target gene.

– Input: relevant documents– Output: gene summary

1. Training data generation

2. Sentence extraction

IE module

Training Data Generation

• Construct a training data set consisting of “typical” sentences for describing a category (e.g., sequence information)

• Training data is not about the gene to be summarized. It is about a “type” of information in general.

• These sentences come from a manually curated database – e.g., Flybase has separate sections for each category.

Sentence Extraction

• Extract sentences from the documents related to our gene

• Then try to identify key sentences talking about a certain aspect of the gene (“category”)

• In determining the importance of a sentence, consider 3 factors– Relevance to the specified category (aspect)– Relevance to its source document– Sentence location in its source abstract

Scoring strategies• Category relevance score (Sc):

– “Vector space model”

– Construct “category term vector” Vc for each category c

– Weight of term ti in this vector is wij=TFij*IDFi

• TFij is frequency of ti in all training sentences of category j

• IDFi is “inverse document frequency” = 1+log(N/ni), N = total # documents, ni = number of documents containing ti.

• TF measures how relevant the term is, IDF measures how rare it is

– Similarly, vector Vs for each sentence s

– Category relevant score Sc = cosine(Vc, Vs )

Scoring strategies

• Document relevance score (Sd):– Sentence should also be related to this document.

– Vd for each document, Sd = cos(Vd, Vs )

• Location score (Sl):– News: early sentences are more useful for summarization

– Scientific literature: last sentence of abstract

– Sl = 1 for the last sentence of an abstract, 0 otherwise.

• Sentence Ranking: S=0.5Sc+0.3Sd+0.2Sl

Summary generation

• Keep only 2 top-ranked categories for each sentence.

• Generate a paragraph-long summary by combining the top sentence of each category

Outline

• Introduction– Motivation– Related Work

• System– Keyword Retrieval Module– Information Extraction Module

• Experiments and Evaluations• Conclusion and Future Work

Experiments

• 22092 PubMed abstracts on “Drosophila”

• Implementation on top of Lemur Toolkit– Variety of information retrieval functions

• 10 genes are randomly selected from Flybase for evaluation

Evaluation

• Precision of the top k sentences for a category evaluated• Three different methods evaluated:

– Baseline run (BL): randomly select k sentences– CatRel: use Category Relevance Score to rank sentences and select

the top-k– Comb: Combine three scores to rank sentences

• Ask two annotators with domain knowledge to judge the relevance for each category

• Criterion: A sentence is considered to be relevant to a category if and only if it contains information on this aspect, regardless of its extra information, if any.

Precision of the top-k sentences

Discussion

• Improvements over the baseline are most pronounced for EL, SI, MP, GI categories. – These four categories are more specific and thus easier

to detect than the other two GP, WFPI.• Problem of predefined categories

– Not all genes fit into this framework. E.g., gene Amy-d, as an enzyme involved in carbohydrate metabolism, is not typically studied by genetic means, thus low precision of MP, GI.

– Not a major problem: low precision in some occasions is probably caused by the fact that there is little research on this aspect.

Summary example (Abl)

Summary example (Camo|Sod)

Outline

• Introduction– Motivation– Related work

• System– Keyword Retrieval Module– Information Extraction Module

• Experiments and evaluations• Conclusion and future work

Conclusion and future work

• Proposed a novel problem in biomedical text mining: automatic structured gene summarization

• Developed a system using IR techniques to automatically summarize information about genes from PubMed abstracts

• Dependency on the high-quality training data in FlyBase– Incorporate more training data from other model

organisms database and resources such as GeneRIF in Entrez Gene

– Mixture of data from different resources will reduce the domain bias and help to build a general tool for gene summarization.

References

1. L. Hirschman, J. C. Park, J. Tsujii, L. Wong, C. H. Wu, (2002) Accomplishments and challenges in literature data mining for biology. Bioinformatics 18(12):1553-1561.

2. H. Shatkay, R. Feldman, (2003) Mining the Biomedical Literature in the Genomic Era: An Overview. JCB, 10(6):821-856.

3. D. Marcu, (2003) Automatic Abstracting. Encyclopedia of Library and Information Science, 245-256.

Vector Space Model

• Term vector: reflects the use of different words• wi,j: weight of term ti in vactor j